© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12813
    Prev
    Next
    INDEX
    Explanations

    words from a mix of Southeast Asian languages and/or words related to eating implements

    oai_token-act-pair · gemini-2.0-flash

    "tine" and foreign language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -2.50
     itſelf
    -2.45
     pleaſure
    -2.33
     ſeveral
    -2.28
    ſelf
    -2.20
     themſelves
    -2.20
     Monfieur
    -2.20
     ―――――
    -2.17
     iſt
    -2.17
     Majefty
    -2.14
    POSITIVE LOGITS
    InjectAttribute
    1.26
     maux
    1.22
     cser
    1.20
     boire
    1.18
    (!__
    1.18
     ferons
    1.16
     fédé
    1.16
     tromper
    1.16
     marito
    1.16
     refroid
    1.16
    Activations Density 5.520%

    No Known Activations